Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Adversarial detection on Expanded benchmark
Loading...
20
Caught Count
Theoria
17.92
18.46
19
19.54
Jul 1, 2026
Caught Count
Detection Rate
Updated 24d ago
Evaluation Results
Method
Method
Links
Caught Count
Detection Rate
Theoria
Model=GPT-5.5, Web sea...
2026.07
20
100
Holistic judge
Model=GPT-5.5, Web sea...
2026.07
18
90
Feedback
Search any
task
Search any
task
